Triple

T19593236
Position Surface form Disambiguated ID Type / Status
Subject R.I.P.D. E470287 entity
Predicate starring P1507 FINISHED
Object Stephanie Szostak NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Stephanie Szostak | Statement: [R.I.P.D., starring, Stephanie Szostak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stephanie Szostak
Context triple: [R.I.P.D., starring, Stephanie Szostak]
  • A. Stephanie Szostak chosen
    Stephanie Szostak is a French-American actress known for her film and television roles, including a prominent part in the drama series "A Million Little Things."
  • B. Myriam P. Sarachik
    Myriam P. Sarachik was a Belgian-born American experimental physicist renowned for her work in low-temperature condensed matter physics and for her leadership and advocacy within the physics community.
  • C. Suzanne Holman
    Suzanne Holman, later known as Suzanne Farrington, was the daughter of famed actress Vivien Leigh and a British woman who largely lived outside the public spotlight.
  • D. Debra Fischer
    Debra Fischer is an American astronomer renowned for her pioneering work in the detection and characterization of exoplanets.
  • E. Marcia Strassman
    Marcia Strassman was an American actress best known for her roles in the sitcom "Welcome Back, Kotter" and the "Honey, I Shrunk the Kids" film series.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640782e2c8190b5baef07a2bdd015 completed April 20, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:43 p.m.